Public defence in Information and Computer Science, Lis.Sc.(Tech) Antti Keurulainen

Title of the thesi: Real-time and sample-efficient learning of computationally rational user models

Doctoral student: Antti Keurulainen
Opponent: Dr. John Williamson, University of Glasgow, Great Britain
Custos: Prof. Samuel Kaski, Aalto University School of Science, Department of Computer Science

To effectively collaborate with humans, Artificial Intelligence (AI) systems must understand human behavior and the factors influencing it, including their goals, preferences, and abilities. Interactions with humans are typically costly, and in many real-life situations, AI must adapt to human behavior after only a few interactions. Additionally, when AI interacts with humans to learn about their behavior, the interactions need to be conducted without any noticeable delay for the human, which in turn necessitates adaptation in real-time. This thesis investigates how an AI system can learn about other agents in a sample-efficient and real-time manner, using methods based on reinforcement learning. The first contribution of this thesis is a method for learning representations of goal-driven agents' behaviors with neural networks from incomplete observations, showing that they can be used for improving performance in cooperative decision-making tasks. The second contribution concerns the creation of an automated method for producing task distributions and related ground truth data for training a meta-learner to assess the skill level and adapt quickly to the behavior of a cooperating partner. The third contribution presents a novel method for designing informative experiments for estimating the parameters of simulation-based user models, which are grounded in cognitive science. The results of the research offer new possibilities to improve cooperation between machines and humans, as well as advance the learning of human-like behavior by artificial intelligence in an interactive environment with limited data.

Key words: Reinforcement Learning, Deep Learning, user models.

Thesis available for public display 10 days prior to the defence at: https://aaltodoc.aalto.fi/doc_public/eonly/riiputus/ 

Contact information:

Doctoral theses at the School of Science: https://aaltodoc.aalto.fi/handle/123456789/52